Puzzle Solving Model Ranking

See which AI models perform best on Puzzle Solving, which ones stay reliable, and where the biggest gaps appear. Sort by: Response Time (avg) ↓.

Models Shown

Average Puzzle Solving Score

0.7

Best Model

Xing4.0 29b A4b 0.3

Failure Reasons

With failure reason Wrong answer352 With failure reason Did not follow instructions166 With failure reason API error35 With failure reason Extra formatting16 With failure reason No answer14 With failure reason Timed out11

451/451

Rank	Model	Company	Puzzle Solving Score	Score	Total Cost	Tests Correct	Response Time (avg)
#373	DeepSeek V3.2 none	DeepSeek	0.8	0.5	$0.119	2/3	6.91s
Total Tests 3 Wrong Tests 1 Total Cost $0.119 Response Time (avg) 6.91s
#86	Gemini 3.1 Pro Preview medium	Google	1.0	0.8	$1.585	3/3	6.90s
Total Tests 3 Wrong Tests 0 Total Cost $1.585 Response Time (avg) 6.90s
#33	GPT-5.5 medium	OpenAI	1.0	0.9	$4.809	3/3	6.76s
Total Tests 3 Wrong Tests 0 Total Cost $4.809 Response Time (avg) 6.76s
#72	Muse Spark 1.1 low	Meta	0.8	0.9	$0.885	2/3	6.60s
Total Tests 3 Wrong Tests 1 Total Cost $0.885 Response Time (avg) 6.60s
#214	Ember-1 max	Fireworks	0.8	0.7	$3.264	2/3	6.57s
Total Tests 3 Wrong Tests 1 Total Cost $3.264 Response Time (avg) 6.57s
#382	Ling 2.6 Flash default	Inclusionai	0.3	0.5	$0.002	0/3	6.51s
Total Tests 3 Wrong Tests 3 Total Cost $0.002 Response Time (avg) 6.51s
#146	Space Bunny Alpha high	Stealth	0.8	0.8	$0.000	2/3	6.43s
Total Tests 3 Wrong Tests 1 Total Cost $0.000 Response Time (avg) 6.43s
#166	Qwen3.6 Plus medium	Qwen	1.0	0.7	$0.554	3/3	6.34s
Total Tests 3 Wrong Tests 0 Total Cost $0.554 Response Time (avg) 6.34s
#152	Qwen3.6 Flash medium	Qwen	0.8	0.7	$0.783	2/3	6.29s
Total Tests 3 Wrong Tests 1 Total Cost $0.783 Response Time (avg) 6.29s
#266	Grok 4.20 medium	X AI	0.8	0.6	$1.246	2/3	6.22s
Total Tests 3 Wrong Tests 1 Total Cost $1.246 Response Time (avg) 6.22s
#378	Nemotron 3.5 Lightning low	NVIDIA	0.4	0.5	$0.175	0/3	6.21s
Total Tests 3 Wrong Tests 3 Total Cost $0.175 Response Time (avg) 6.21s
#129	Step 3.7 Flash medium	Stepfun	0.6	0.8	$0.571	1/3	6.19s
Total Tests 3 Wrong Tests 2 Total Cost $0.571 Response Time (avg) 6.19s
#34	Claude Sonnet 5.5 max	Anthropic	1.0	0.9	$8.557	3/3	6.17s
Total Tests 3 Wrong Tests 0 Total Cost $8.557 Response Time (avg) 6.17s
#118	Claude Fable 5.1 high	Anthropic	1.0	0.8	$3.471	3/3	6.11s
Total Tests 3 Wrong Tests 0 Total Cost $3.471 Response Time (avg) 6.11s
#339	Nemotron 3.5 Lightning high	NVIDIA	0.4	0.5	$0.168	0/3	6.09s
Total Tests 3 Wrong Tests 3 Total Cost $0.168 Response Time (avg) 6.09s

Puzzle Solving Ranking

Filter models

Top Models by Puzzle Solving Score

Puzzle Solving Score vs Total Cost

Top Models by Response Time (avg)